typesafeai-review
Using Typesafe.AI to generate diff reviews.
How it uses Jev
A code reviewer built as AI-powered software, not an LLM agent. Code runs the checks, slices the diff, asks Jev (TypeSafe's System One model) narrow typed questions per hunk, and composes verdict, score and findings in code. Ships as a standalone dev dependency ( uv run review --worktree ). Spec: docs/specs/typesafe-reviewer.md .
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.